SlimOrca-13B: benchmark results
A full Llama-2 fine-tune by ajibawa-2023 on 517,981 conversation sets derived from Open-Orca/SlimOrca and repackaged as SlimOrca-ShareGPT. Dataset authorship remains credited to Open-Orca. Provider: ajibawa-2023. Access: Open.
Aggregate Rating 1371 ± 33, rank #7146 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 39.95 | Accuracy (%) (5-shot) | 55.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 60.15 | Normalized accuracy (%) (25-shot) | 46.6 |
| Open LLM Leaderboard v1 - HellaSwag | 81.4 | Normalized accuracy (%) (10-shot) | 44.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 49.37 | MC2 (%) (0-shot) | 44.5 |
| Open LLM Leaderboard v1 - MMLU | 57.04 | Accuracy (%) (5-shot) | 40.5 |
| Open LLM Leaderboard v1 - WinoGrande | 74.43 | Accuracy (%) (5-shot) | 36.5 |
Interactive version: theaggregate.ai/model?slug=slimorca-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.